A Bayesian active learning method with statistical feature engineering and multi-output Gaussian processes selects target hyperelastic metamaterial designs from 50,000 candidates using under 0.5% high-fidelity oracle calls.
Data-driven inverse design of spinodoid architected materials.GAMM-Mitteilungen, 48, 2025
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
LEAP enables real-time proprioceptive adaptation to unseen damage in a 6DoF soft wrist using HSA actuators by combining latent damage representations with a robust ensemble method, with conditions identified for linear rather than exponential sample complexity.
citing papers explorer
-
Data-efficient Bayesian-guided design selection from large candidate sets: Application to hyperelastic stochastic metamaterials
A Bayesian active learning method with statistical feature engineering and multi-output Gaussian processes selects target hyperelastic metamaterial designs from 50,000 candidates using under 0.5% high-fidelity oracle calls.
-
Damage Adaptation in Seconds for Architected Materials
LEAP enables real-time proprioceptive adaptation to unseen damage in a 6DoF soft wrist using HSA actuators by combining latent damage representations with a robust ensemble method, with conditions identified for linear rather than exponential sample complexity.